Data Catalog

Your data warehouses may have tons of tables with convoluted logic that are difficult to navigate, for both human and LLMs. Cocoon catalogs what each table is for, how they are connected and what is the business process behind.

Get Started

Open Source

Full Features

Cocoon is open-source. Try out Cocoon in Google Colab.

Cocoon connects to your data warehouses (e.g., Snowflake, Duckdb...) and uses LLMs (e.g., GPT-4, Claude-3, Gemini-Ultra, or your local LLMs) to standardize tables.

Need support or have questions? Contact Us

Gallery

More example data catalogs, mostly from fivetran data source

Amazon Ads

Fivetran Amazon Ads Source

Apple Store

Fivetran Apple Store Source

Asana

Fivetran Asana Source

Facebook Ads

Fivetran Facebook Ads Source

HubSpot

Fivetran HubSpot Source

Jira

Fivetran Jira Source

LinkedIn

Fivetran LinkedIn Source

Pinterest

Fivetran Pinterest Source

Qualtrics

Fivetran Qualtrics Source

SAP

Fivetran SAP Source

Salesforce

Fivetran Salesforce Source

Salesforce (Large)

Fivetran Salesforce (large with ~500 tables)

Shopify

Fivetran Shopify Source

Stripe

Fivetran Stripe Source

Twilio

Fivetran Twilio Source

Zendesk

Fivetran Zendesk Source

OMOP

OMOP Common Data Model

Retail Bank

Retail Bank

Synthea

Synthetic Patient Generation

SSB

Star Schema Benchmark

TPC-DS

TPC-DS

TPC-H

TPC-H

StreetEasy

StreetEasy Metrics

Research

Coming soon...